Beyond the conventional: Exploring pedestrian safety on interstates with Bayesian and machine learning models.

Introduction: Despite being prohibited from walking on freeways per federal laws, 14% to 17% of all pedestrian crashes in the United States happen on the interstates. Examining these crashes within the context of the safe systems approach is essential, with an emphasis on mitigating safety risks for all road users. This study investigates the correlates of pedestrian crash injury severity on interstates in North Carolina, focusing on pedestrian actions, roadway conditions, and the type of vehicles involved in the crashes. The study utilizes police-reported pedestrian crash data from 2007 to 2022, coded by the Pedestrian and Bicyclist Crash Analysis Tool (PBCAT), providing unique and comprehensive crash descriptors. The analysis considers 882 pedestrian crash observations on freeways. The dependent variable, pedestrian injury severity, is categorized into distinct binary outcomes: fatal and severe injuries versus minor injuries.

Methods: The study applies frequentist and Bayesian binary logit models with various prior specificationsand a robust machine learning algorithm, Random Forest, for their ability to provide reliable estimates even with a limited sample size.

Results: The results show that pedestrian crashes are more predominant in rural (47%) than urban freeways (40%) in North Carolina. Key findings indicate that crashes involving pedestrians standing on the road (odds ratio = 2.40), crossing the freeway (odds ratio = 1.645), impaired with alcohol (odds ratio = 2.51), and crashes on dark unlit segments of freeways (odds ratio = 2.00) are associated with a higher risk of severe injuries to pedestrians.

Conclusions And Practical Applications: The study highlights the need for a multi-tiered approach to improving freeway pedestrian safety, aligning with the Safe Systems Pyramid framework. It proposes strategies such as improving roadway lighting, variable speed limits at night, and applying transportation technologies to notify drivers of pedestrian presence to improve pedestrian safety on freeways.